Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation Extraction
Not on the map. Why?
Abstract (arXiv)
This paper presents several strategies to automatically obtain additional examples for in-context learning, effectively transforming relation extraction from a 1-shot to a few-shot setting. Specifically, we introduce a novel strategy for example selection, in which new examples are selected based on the similarity of their underlying syntactic-semantic structure to the provided 1-shot example. We show that our strategy results in complementary word choices and sentence structures compared to LLM-generated examples. When both strategies are combined, the resulting hybrid system achieves a more holistic picture of the relations of interest than either method alone. Our framework transfers well across datasets (FS-TACRED and FS-FewRel) and LLM families (Qwen and Gemma). Overall, our hybrid system consistently outperforms alternative strategies achieving state-of-the-art performance on FS-TACRED and strong gains on a customized FewRel subset.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 28 Jan 2026.
Builds on
25 of 46 references.
References · 25
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
- 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
- 2023Finding Support Examples for In-Context Learningcited by 104
- 2023In-Context Learning with Iterative Demonstration Selectioncited by 74
- 2019Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extractioncited by 73
- 2022A Decade of Knowledge Graphs in Natural Language Processing: A Surveycited by 40
- 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 39
13 more
- 2023How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?cited by 30
- 2021Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemescited by 27
- 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentationcited by 24
- 2024C-ICL: Contrastive In-context Learning for Information Extractioncited by 23
- 2023Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extractioncited by 19
- 2024Learning to Retrieve Iteratively for In-Context Learningcited by 13
- 2025Exploring the Role of Diversity in Example Selection for In-Context Learningcited by 12
- 2023Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairscited by 10
- 2023RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extractioncited by 9
- 2024Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classificationcited by 6
- 2023Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extractioncited by 5
- 2022From Examples to Rules: Neural Guided Rule Synthesis for Information Extractioncited by 4
- 2024Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluationcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.